REVIEW 6 cited by
Let us Build Bridges: Understanding and Extending Diffusion Generative Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Diffusion-based generative models have achieved promising results recently, but raise an array of open questions in terms of conceptual understanding, theoretical analysis, algorithm improvement and extensions to discrete, structured, non-Euclidean domains. This work tries to re-exam the overall framework, in order to gain better theoretical understandings and develop algorithmic extensions for data from arbitrary domains. By viewing diffusion models as latent variable models with unobserved diffusion trajectories and applying maximum likelihood estimation (MLE) with latent trajectories imputed from an auxiliary distribution, we show that both the model construction and the imputation of latent trajectories amount to constructing diffusion bridge processes that achieve deterministic values and constraints at end point, for which we provide a systematic study and a suit of tools. Leveraging our framework, we present 1) a first theoretical error analysis for learning diffusion generation models, and 2) a simple and unified approach to learning on data from different discrete and constrained domains. Experiments show that our methods perform superbly on generating images, semantic segments and 3D point clouds.
Forward citations
Cited by 6 Pith papers
-
Faster Diffusion Models via Higher-Order Approximation
A new higher-order ODE sampler for diffusion models is proven to reach ε total-variation accuracy with eO(d^{1+2/K}/ε^{1/K}) iterations under mild assumptions.
-
Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation
PURE achieves an Õ(√(d_R+d_F)/√N) suboptimality gap, up to horizon factors, in continuous-time RL with general function approximation, and adds low-switching and low-rollout variants.
-
Conditional Flow Matching for Visually-Guided Acoustic Highlighting
Conditional flow matching with a rollout loss and early audio-visual fusion achieves state-of-the-art results on visually-guided acoustic highlighting.
-
A Gaussian Perspective for Distributional Discrepancy in Generative Diffusion Models
For Gaussian sources, diffusion sampling error has a closed-form KL whose leading term is minimized by a tangent-law noise schedule, and the same KL guides low-NFE time discretization on real images.
-
Source Separation by Flow Matching
FLOSS applies flow matching on the subspace orthogonal to the mixture average to generate source-separated signals that exactly sum to the observed mixture.
-
Non-asymptotic convergence bound of conditional diffusion models
CARD's generated conditional distribution is shown to converge in Wasserstein distance to the true conditional distribution, with a separate score-estimation error bound controlled by network resolution and distributi...
Discussion (0). Sign in to comment.